Viewing profile — elyase

there is also pz a drop-in replacement for pi rewritten in Zig. 1.7MB static binary, 3ms startup, 1.4MB RAM idle. Find more at: https://github.com/elyase/awesome-personal-ai-assist…

https://github.com/sst/opencode

This is similar to the tool call (fixed code & dynamic params) vs code generation (dynamic code & dynamic params) discussion: tools offer contrains and save tokens, code gives you …

Between two models the one with the shorter Minimum Description Length (MDL) will more likely generalize better

What you're missing is how to use the tools properly. With solid documentation, good project management practices, a well-organized code structure and tests, any junior engineer sh…

I want to use browser-use in Cursor but I am using another option because it doesn't support MCP integration which is the common language they support for external tools

There is more information in these twitter threads: https://x.com/karinanguyen_/status/1879270529066262733 https://x.com/OpenAI/status/1879267276291203329

How does it compare to https://github.com/explodinggradients/ragas

The closest alternatives in this space would be allennlp [1], the recently released pytext [2] and spacy [3]. pytext's authors wrote some comparison on the accompanying paper [4] a…

We have done extensive testing in the context of chatbot intent classification and in our particular problem nothing (including CNN, LSTM, fasttext plus LUIS, Watson and other prop…

Take a look here for some solutions: https://www.openmined.org

fast.ai is great and I also want to love it but I find the coding style extremely unconventional and uninviting to the point that I only use the library when there is really no bet…

Cool project. Are you also going to allow access to the historical data?

Dask would be an option.

We evaluated using ConceptNet Numberbatch but in the end went with fasttext because of the treatment of OOV words using sub word information. This is important for us because we wo…

It can be argued that some algorithms like Random Forests don't impose a generalization penalty as you increase the number of parameters (forests).

If you follow the right people in your fields of interest you will have an endless stream of interesting updated content. You can't personalize HN to have the exact sort of news yo…

Great work! A question: how do we scale the computations? I know how long my experiments normally take on a 40 core PC. How long will it take and how much will it cost if I use Emp…

A study assessing 6 months (n=112) and 12 months (n=96) of melatonin treatment of 2mg in a controlled release capsule, taken 1-2 hours prior to sleep, people aged 20-80 with primar…